Set Of Configurations Research Articles

Influence on Sample Determination for Deep Learning Electromagnetic Tomography

Deep learning (DL) has been frequently applied in the image reconstruction of electromagnetic tomography (EMT) in recent years. It offers the potential to achieve higher-quality image reconstruction. Among these, research on samples is relatively scarce. Samples are the cornerstone for both large and small models, which is easy to ignore. In this paper, a deep learning electromagnetic tomography (DL-EMT) model with nine elements is established. Complete simulation and experimental samples are obtained based on this model. On the sample sets, the reconstruction quality is observed by adjusting the size and configuration of the training set. The Mann–Whitney U test shows that beyond a certain point, the addition of more samples to the training data fed into the deep learning network does not result in an obvious improvement statistically in the quality of the reconstructed images. This paper proposes a CC-building method for optimizing a sample set. This method is based on the Pearson correlation coefficient calculation, aiming to establish a more effective sample base for DL-EMT image reconstruction. The statistical analysis shows that the CC-building method can significantly improve the image reconstruction effect in a small and moderate sample size. This method is also validated by experiments.

Design and Characterization of Soft Fabric Omnidirectional Bending Actuators

Soft robots, inspired by biological adaptability, can excel where rigid robots may falter and offer flexibility and safety for complex, unpredictable environments. In this paper, we present the Omnidirectional Bending Actuator (OBA), a soft robotic actuation module which is fabricated from off-the-shelf materials with easy scalability and consists of three pneumatic chambers. Distinguished by its streamlined manufacturing process, the OBA is capable of bending in all directions with a high force-to-weight ratio, potentially addressing a notable research gap in knit fabric actuators with multi-degree-of-freedom capabilities. We will present the design and fabrication of the OBA, examine its motion and force capabilities, and demonstrate its capability for stiffness modulation and its ability to maintain set configurations under loads. The mass of the entire actuation module is 278 g, with a range of omnidirectional bending up to 90.80°, a maximum tolerable pressure of 862 kPa, and a bending payload (block force) of 10.99 N, resulting in a force-to-weight ratio of 39.53 N/kg. The OBA’s cost-effective and simple fabrication, compact and lightweight structure, and capability to withstand high pressures present it as an attractive actuation primitive for applications demanding efficient and versatile soft robotic solutions.

Preliminary analysis of stimulation parameters for sacral neuromodulation in different indications: A multi-center retrospective cohort study from China.

Sacral neuromodulation (SNM) is an effective approach for treating lower urinary tract dysfunction (LUTD), and stimulation programming is essential for successful treatment. However, research on SNM programming for various indications is limited. Thus, we aimed to determine whether there were differences in the stimulation parameters for different SNM indications and the appropriate programming recommendations. Clinical data were retrospectively collected from patients with LUTD who underwent SNM and completed internal pulse generator (IPG) implantation. The parameters with the highest patient satisfaction or the most symptom improvement during the test period were considered optimal and used to set the programming after IPG implantation. After screening, 282 patients were enrolled and categorized into four groups based on the following indications: refractory overactive bladder (OAB) (n=61), neurogenic lower urinary tract dysfunction (nLUTD) (n=162), interstitial cystitis/painful bladder syndrome (IC/BPS) (n=24), and idiopathic non-obstructive urinary retention (NOUR) (n=35). When analyzing the optimal stimulus parameters, disparities in the stimulation amplitude and pulse frequency were noted among the four groups. The stimulation amplitude in the nLUTD group was higher than that in the idiopathic NOUR group (P=0.013). Differences in pulse frequency were observed between the refractory OAB and nLUTD groups (P<0.001) and between the refractory OAB and idiopathic NOUR groups (P=0.001). No differences in the electrode configuration or pulse width settings existed among the four groups. The stimulation parameters for SNM varied among the different indications. For the initial programming of stage I, most patients are recommended to start with stimulation amplitudes below 2 V, although patients with nLUTD may benefit from higher amplitudes. A standard pulse width of 210μs is recommended for all patients. However, for individuals experiencing nLUTD or idiopathic NOUR, the pulse frequency can begin above the standard 14Hz but not exceed 50Hz.

Robust errant beam prognostics with conditional modeling for particle accelerators

Particle accelerators are complex and comprise thousands of components, with many pieces of equipment running at their peak power. Consequently, they can fault and abort operations for numerous reasons, lowering efficiency and science output. To avoid these faults, we apply anomaly detection techniques to predict unusual behavior and perform preemptive actions to improve the total availability. Supervised machine learning (ML) techniques such as siamese neural network models can outperform the often-used unsupervised or semi-supervised approaches for anomaly detection by leveraging the label information. One of the challenges specific to anomaly detection for particle accelerators is the data’s variability due to accelerator configuration changes within a production run of several months. ML models fail at providing accurate predictions when data changes due to changes in the configuration. To address this challenge, we include the configuration settings into our models and training to improve the results. Beam configurations are used as a conditional input for the model to learn any cross-correlation between the data from different conditions and retain its performance. We employ conditional siamese neural network (CSNN) models and conditional variational auto encoder (CVAE) models to predict errant beam pulses at the spallation neutron source under different system configurations and compare their performance. We demonstrate that CSNNs outperform CVAEs in our application.

OMNeT++ Simulation Framework for Avionics Full-Duplex Switched Ethernet

Avionics Full-Duplex Switched Ethernet (AFDX) is a popular network technology for integrated modular avionics (IMA). When designing an AFDX network, it is important to fulfill the real-time communication requirements of avionic systems. To this end, simulation tools offer a low-cost solution for the performance evaluation of a given AFDX network and message set configuration at the design stage. In this paper, we develop an improved AFDX model for the widely used OMNeT++ (extensible, modular, component-based C++ simulation library and framework) network simulator. Our model exhibits high fidelity to the standard, adds detailed parameter configuration and data logging capabilities, and is compatible with the most recent OMNeT++ version. Our model is accepted by the OMNeT++ community and published as the current AFDX simulation model. Moreover, we propose a complete AFDX simulation framework by augmenting our improved OMNeT++ models with a new network configuration and analysis software tool that we call ANCAT. ANCAT enables users who lack familiarity with the OMNeT++ interface and specific file formats to provide simulation parameters in generic file formats such as.xlsx. Subsequently, ANCAT runs the simulation and generates reports for the results. We first systematically verify the correctness of our AFDX simulation framework by custom-designed experiments. Then, we investigate the practicability of our proposed framework with the performance analysis of a realistic AFDX network topology and message set. In particular, we demonstrate that our proposed framework can be efficiently used to explore the real-time capabilities and relevant features of AFDX networks, as well as provide basic guidelines for network configuration.

Minimal configuration point cloud odometry and mapping

Simultaneous Localization and Mapping (SLAM) refers to the common requirement for autonomous platforms to estimate their pose and map their surroundings. There are many robust and real-time methods available for solving the SLAM problem. Most are divided into a front-end, which performs incremental pose estimation, and a back-end, which smooths and corrects the results. A low-drift front-end odometry solution is needed for robust and accurate back-end performance. Front-end methods employ various techniques, such as point cloud-to-point cloud (PC2PC) registration, key feature extraction and matching, and deep learning-based approaches. The front-end algorithms have become increasingly complex in the search for low-drift solutions and many now have large configuration parameter sets. It is desirable that the front-end algorithm should be inherently robust so that it does not need to be tuned by several, perhaps many, configuration parameters to achieve low drift in various environments. To address this issue, we propose Simple Mapping and Localization Estimation (SiMpLE), a front-end LiDAR-only odometry method that requires five low-sensitivity configurable parameters. SiMpLE is a scan-to-map point cloud registration algorithm that is straightforward to understand, configure, and implement. We evaluate SiMpLE using the KITTI, MulRan, UrbanNav, and a dataset created at the University of Queensland. SiMpLE performs among the top-ranked algorithms in the KITTI dataset and outperformed all prominent open-source approaches in the MulRan dataset whilst having the smallest configuration set. The UQ dataset also demonstrated accurate odometry with low-density point clouds using Velodyne VLP-16 and Livox Horizon LiDARs. SiMpLE is a front-end odometry solution that can be integrated with other sensing modalities and pose graph-based back-end methods for increased accuracy and long-term mapping. The lightweight and portable code for SiMpLE is available at: https://github.com/vb44/SiMpLE .

Evaluation of security framework for BYOD device in cloud environment

The widespread practice of Bring your own device (BYOD) to work significantly raises cybersecurity risks. All organization’s employees and employers will greatly benefit from this trend. The growth of spyware, malware and other dubious downloads on individual devices has compelled the government to review its data security guidelines. Without user knowledge, hazardous apps are downloaded to personal devices. Both people and governments could suffer tragic consequences as a result of this. In this situation, BYODs are problematic since they can alter policies without permission and release private information. The main goal of the research was to detect fraudulent communications coming from BYOD environments. A network monitoring and managing information configuration settings of mobile devices in the network is established by providing policies and authenticating endpoint devices in the BYOD network using a mix of NAC and MDM. This framework deals with Security Manager (SaaS) as the second module is briefly described. The study's early results were positive and suggested that the framework would lessen access control-related issues.

The effect of rest redistribution on kinetic and kinematic variables during the hang pull.

The aim of this study was to compare the effects of rest redistribution (RR) on kinetics and kinematics during the hang pull (HP). Twenty-one male athletes (age 29.5 ± 4.3 years, height 1.78 ± 0.07 m, body mass 75.17 ± 11.11 kg, relative one repetition maximum [1RM] power clean [PC] 1.17 ± 0.14 kg.kg-1) performed the HP using 140% of 1RM PC with 3 traditional sets of 6 repetitions (TS), 9 sets of 2 repetitions with RR [45s rest after 2 repetitions] (RR45) and 6 sets of 3 repetitions with RR [72s rest after 3 repetitions] (RR72). Peak velocity (PV) was higher during RR72 (1.18 ± 0.11 m.s-1) compared to RR45 (1.14 ± 0.11 m.s-1) for the average of 18 repetitions (p = 0.025, g = 0.36). There was a main effect for set configuration with greater peak force (PF) (p < 0.001, g = 0.14) during RR72 compared to RR45, with greater PV and impulse (p < 0.001, g = 0.19-0.36) during RR72 compared to RR45. There was also greater peak velocity maintenance (PVM) (p = 0.042, g = 0.44) for RR72 compared to RR45. There were no significant or meaningful differences (p > 0.05, g = 0.00-0.59) between configurations for any other variables. Rest redistribution protocols did not result in significantly or meaningfully greater kinetics or kinematics during the HP when compared to a TS protocol; although performing RR72 resulted in higher PF, PV, and impulse, with improved PVM compared to RR45.

Assessing CESM2 clouds and their response to climate change using cloud regimes

Abstract The Community Earth System Model, version 2 (CESM2) has a very high climate sensitivity driven by strong positive cloud feedbacks. To evaluate the simulated clouds in the present climate and characterize their response with climate warming, a clustering approach is applied to three independent satellite cloud products and a set of coupled climate simulations. Using k-means clustering with a Wasserstein distance cost function, a set of typical cloud configurations is derived for the satellite cloud products. Using satellite simulator output, the model clouds are classified into the observed cloud regimes in both current and future climates. The model qualitatively reproduces the observed cloud configurations in the historical simulation using the same time period as the satellite observations, but it struggles to capture the observed heterogeneity of clouds which leads to an overestimation of the frequency of a few preferred cloud regimes. This problem is especially apparent for boundary layer clouds. Those low-level cloud regimes also account for much of the climate response in the late 21st Century in four Shared Socioeconomic Pathway simulations. The model reduces the frequency of occurrence of these low-cloud regimes, especially in tropical regions under large-scale subsidence, in favor of regimes that have weaker cloud radiative effects.

On Uniqueness in Steiner Problem

Abstract We prove that the set of $n$-point configurations for which the solution to the planar Steiner problem is not unique has the Hausdorff dimension at most $2n-1$ (as a subset of $\mathbb{R}^{2n}$). Moreover, we show that the Hausdorff dimension of the set of $n$-point configurations for which at least two locally minimal trees have the same length is also at most $2n-1$. The methods we use essentially rely upon the theory of subanalytic sets developed in [ 1]. Motivated by this approach, we develop a general setup for the similar problem of uniqueness of the Steiner tree where the Euclidean plane is replaced by an arbitrary analytic Riemannian manifold $M$. In this setup, we argue that the set of configurations possessing two locally-minimal trees of the same length either has dimension equal to $n \dim M - 1$ or has a non-empty interior. We provide an example of a two-dimensional surface for which the last alternative holds. In addition to the above-mentioned results, we study the set of $n$-point configurations for which there is a unique solution to the Steiner problem in $\mathbb{R}^{d}$. We show that this set is path-connected.

On restricted Falconer distance sets

Abstract We introduce a class of Falconer distance problems, which we call of restricted type, lying between the classical version and its pinned variant. Prototypical restricted distance sets are the diagonal distance sets, k-point configuration sets given by $$ \begin{align*}\Delta^{\mathrm{diag}}(E)= \{ \,|(x,x,\dots,x)-(y_1,y_2,\dots,y_{k-1})| : x, y_1, \dots,y_{k-1} \in E\, \}\end{align*} $$ for a compact $E\subset \mathbb {R}^d$ and $k\ge 3$ . We show that $\Delta ^{\mathrm{diag}}(E)$ has non-empty interior if the Hausdorff dimension of E satisfies (0.1) $$ \begin{align} \dim(E)&gt; \begin{cases} \frac{2d+1}3, &amp; k=3, \\ \frac{(k-1)d}k,&amp; k\ge 4. \end{cases} \end{align} $$ We prove an extension of this to $C^\omega $ Riemannian metrics g close to the product of Euclidean metrics. For product metrics, this follows from known results on pinned distance sets, but to obtain a result for general perturbations g, we present a sequence of proofs of partial results, leading up to the proof of the full result, which is based on estimates for multilinear Fourier integral operators.

Deep reinforcement learning and convolutional autoencoders for anomaly detection of congenital inner ear malformations in clinical CT images

Detection of abnormalities within the inner ear is a challenging task even for experienced clinicians. In this study, we propose an automated method for automatic abnormality detection to provide support for the diagnosis and clinical management of various otological disorders. We propose a framework for inner ear abnormality detection based on deep reinforcement learning for landmark detection which is trained uniquely in normative data. In our approach, we derive two abnormality measurements: Dimage and Uimage. The first measurement, Dimage, is based on the variability of the predicted configuration of a well-defined set of landmarks in a subspace formed by the point distribution model of the location of those landmarks in normative data. We create this subspace using Procrustes shape alignment and Principal Component Analysis projection. The second measurement, Uimage, represents the degree of hesitation of the agents when approaching the final location of the landmarks and is based on the distribution of the predicted Q-values of the model for the last ten states. Finally, we unify these measurements in a combined anomaly measurement called Cimage. We compare our method’s performance with a 3D convolutional autoencoder technique for abnormality detection using the patch-based mean squared error between the original and the generated image as a basis for classifying abnormal versus normal anatomies. We compare both approaches and show that our method, based on deep reinforcement learning, shows better detection performance for abnormal anatomies on both an artificial and a real clinical CT dataset of various inner ear malformations with an increase of 11.2% of the area under the ROC curve. Our method also shows more robustness against the heterogeneous quality of the images in our dataset.

A Conv‐GEMM reconfigurable accelerator with WS‐RS dataflow for high throughput processing

AbstractConvolution and matrix operations are both important computations in Deep Neural Networks (DNNs). However, the significant differences between convolution and matrix computation patterns have posed a challenge in efficiently supporting both convolution (Conv) and general matrix multiplication (GEMM) on hardware design. This paper proposes a Conv‐GEMM reconfigurable accelerator architecture for high throughput edge processing. A weight stationary‐row streaming (WS‐RS) dataflow scheme is proposed, which maximizes data reuse through hierarchical memory structures and flexible PE connections, and supports high throughput edge‐based deep learning algorithms. Based on the proposed dataflow, multi‐scale memory access network (MMAN), reconfigurable accumulator array (RAA), and configurable instruction set architecture (ISA) are designed to optimize computation throughput and energy efficiency. The accelerator is designed under 65 nm technology, achieves peak performance of 1.15 TOPS at 250 MHz, with an energy efficiency of 1.14 TOPS/W. The GEMM computation achieves 85.7% latency improvement and the Mobilenet‐V1 processing achieves a throughput of 529 fps under a 256 × 224 image size and an 87.15% (top‐5) accuracy on the ImageNet dataset.

Exploratory evaluation of spinal cord stimulation with dynamic pulse patterns: a promising approach to improve stimulation sensation, coverage of pain areas, and expected pain relief.

The societal burden of chronic pain and the contribution-in-part to the opioid crisis, is a strong motivation to improve and expand non-addictive treatments, including spinal cord stimulation (SCS). For several decades standard SCS has consisted in delivery of tonic pulses with static parameter settings in frequency, pulse width, and amplitude. These static parameters have limited ability to personalize the quality of paresthesia, the dermatomal coverage, and thus may affect SCS efficacy. Further, static settings may contribute to the build-up of tolerance or loss of efficacy of the therapy over time in some patients. We conducted an acute exploratory study to evaluate the effects of SCS using time-dynamic pulses as compared to time-static (conventional tonic) stimulation pulses, with the hypotheses that dynamic pulse SCS may enable beneficial tailoring of the sensation and the patient's expectation for better pain relief with SCS. During a single clinic visit, consented subjects undergoing a standard SCS trial had their implanted leads temporarily connected to an investigational external stimulator capable of delivering time-static and six categories of time-dynamic pulse sequences, each characterized by continuously varying a stimulation parameter. Study subjects provided several assessments while blinded to the stimulation pattern, including: drawing of paresthesia maps, descriptions of sensation, and ratings for comfort and helpfulness to pain relief. Even without optimization of the field location, a majority of subjects rated sensations from dynamic stimulation as better or equal to that of static stimulation for comfortableness and for helpfulness to pain relief. The initial data showed a gender and/or pain dermatomal location related preference to a stimulation pattern. In particular, female subjects and subjects with pain at higher dermatomes tended to rank the sensation from dynamic stimulation better. Dynamic stimulation produced greater pain coverage without optimization; in 70% (9/13) of subjects, maximal pain coverage was achieved with a dynamic stimulation pattern. There was also greater variety in the words used by patients to describe stimulation sensation in the free text and free form verbal descriptions associated with dynamic stimulation. With the same electrode configuration and comparable parameter settings, acute SCS using dynamic pulses produced more positive ratings, expanded paresthesia coverage, and greater variation in sensation as compared to SCS using static pulses, suggesting that dynamic stimulation has the potential to improve capabilities of SCS for the treatment of chronic pain. Further study is warranted. This study was registered at ClinicalTrials.gov under ID NCT02988713, November 2016 (URL: https://clinicaltrials.gov/ct2/show/NCT02988713).

Cyberattack detection in wireless sensor networks using a hybrid feature reduction technique with AI and machine learning methods

This paper proposes an intelligent hybrid model that leverages machine learning and artificial intelligence to enhance the security of Wireless Sensor Networks (WSNs) by identifying and preventing cyberattacks. The study employs feature reduction techniques, including Singular Value Decomposition (SVD) and Principal Component Analysis (PCA), along with the K-means clustering model enhanced information gain (KMC-IG) for feature extraction. The Synthetic Minority Excessively Technique is introduced for data balancing, followed by intrusion detection systems and network traffic categorization. The research evaluates a deep learning-based feed-forward neural network algorithm's accuracy, precision, recall, and F-measure across three vital datasets: NSL-KDD, UNSW-NB 15, and CICIDS 2017, considering both full and reduced feature sets. Comparative analysis against benchmark machine learning approaches is also conducted. The proposed algorithm demonstrates exceptional performance, achieving high accuracy and reliability in intrusion detection for WSNs. The study outlines the system configuration and parameter settings, contributing to the advancement of WSN security.

Assessment of subvisible particles in biopharmaceuticals with image feature extraction and machine learning

An image classification tool was developed to classify subvisible particles, namely silicone oil (SO) and non-silicone oil (NSO; protein aggregate, rubber closure, and air bubble) particles, present in biopharmaceuticals using feature extraction in FlowCam® images, and the outcomes were validated with six machine learning (ML) classifiers. The image classification tool set at specific configuration: condition 1 − CDEP {(compactness, diameter, elongation, perimeter) = (8.06, 10.44, 13.30, 27.20)} identified SO, while the configuration set at condition 2 – CDEL {(compactness, diameter, elongation, length) = (3.14, 24.48, 1.97, 4.28)} detected NSO. The classification tool was particularly useful in detecting the release of SO after exposure to the stress sources. Additionally, the morphological features-based classification tool (p < 0.05) enhanced the predictive accuracy of the ML classification tools (≥97.2 %). Specifically, CNN (100 %) outperformed naïve Bayes (99.3 %), linear discriminant analysis (98.4 %), artificial neural network (98.1 %), support vector machine (SVM 97.2 %). Bootstrap forest was excluded because it failed to classify SO in a large dataset. The developed classification tool could be an alternative in classifying the image datasets without the burden of complex ML tools. Such image-based classification tool can be computationally economical solution in quality control of the protein formulations.

Exploring Ring Conformation in Uronate Monosaccharides: Insights from Ab Initio Calculations and Classical Molecular Dynamics Simulations.

The study focuses on the conformational properties of biologically relevant monosaccharides belonging to the group of uronates: α-l-iduronate, O2-sulfated-α-l-iduronate, and O2-sulfated-α-l-guluronate, either unfunctionalized or O1-methylated. We applied the previously proposed two-step methodology, combining classical MD simulations and subsequent ab initio (QM) calculations, performed on a rationally subsampled set of molecular configurations. We found that, regardless of the number of molecular configurations considered, the level of theory, and the weighting scheme applied, none of the QM approaches is capable of predicting the correct conformational equilibrium of sulfated iduronates as long as the tight counterion binding is not considered. Multicenter, ring-shape-specific binding of either Na+ or Ca2+ ions drastically shifts the conformational equilibrium of the pyranose ring in sulfated iduronates toward 1C4 but does not significantly affect the conformation of non-sulfated compounds. A similar shift is observed upon the protonation of carboxyl groups in all iduronates. In addition, we report a set of average J-coupling constant values related to vicinal protons bound to the pyranose ring of iduronates and corresponding to each of the three main groups of ring conformers, i.e., 4C1, B/S (boat/skew boat), and 1C4. In combination with the conformational energies or with the experimental data, these values allowed the relative proportions of the ring conformers to be estimated and the Karplus-type equations linking the 3JHH-coupling constants to the torsion angles within the pyranose ring to be refined.

Risk-Based Hosting Capacity Analysis in Distribution Systems

Solar hosting capacity analysis (HCA) assesses the ability of a distribution network to host distributed solar generation without seriously violating distribution network constraints. In this paper, we consider risk-sensitive HCA that limits the risk of network constraint violations with a collection of scenarios of solar irradiance and nodal power demands, where risk is modeled via the conditional value at risk (CVaR) measure. First, we consider the question of maximizing aggregate installed solar capacities, subject to risk constraints and solve it as a second-order cone program (SOCP) with a standard conic relaxation of the feasible set of the power flow equations. Second, we design an incremental algorithm to decide whether a configuration of solar installations has acceptable risk of constraint violations, modeled via CVaR. The algorithm circumvents explicit risk computation by incrementally constructing inner and outer polyhedral approximations of the set of acceptable solar installation configurations from prior such tests conducted. Our numerical examples study the impact of risk parameters, the number of scenarios and the scalability of our framework.

Metafeature Selection via Multivariate Sparse-Group Lasso Learning for Automatic Hyperparameter Configuration Recommendation.

The performance of classification algorithms is mainly governed by the hyperparameter settings deployed in applications, and the search for desirable hyperparameter configurations usually is quite challenging due to the complexity of datasets. Metafeatures are a group of measures that characterize the underlying dataset from various aspects, and the corresponding recommendation algorithm fully relies on the appropriate selection of metafeatures. Metalearning (MtL), aiming to improve the learning algorithm itself, requires development in integrating features, models, and algorithm learning to accomplish its goal. In this article, we develop a multivariate sparse-group Lasso (SGLasso) model embedded with MtL capacity in recommending suitable configurations via learning. The main idea is to select the principal metafeatures by removing those redundant or irregular ones, promoting both efficiency and performance in the hyperparameter configuration recommendation. To be specific, we first extract the metafeatures and classification performance of a set of configurations from the collection of historical datasets, and then, a metaregression task is established through SGLasso to capture the main characteristics of the underlying relationship between metafeatures and historical performance. For a new dataset, the classification performance of configurations can be estimated through the selected metafeatures so that the configuration with the highest predictive performance in terms of the new dataset can be generated. Furthermore, a general MtL architecture combined with our model is developed. Extensive experiments are conducted on 136 UCI datasets, demonstrating the effectiveness of the proposed approach. The empirical results on the well-known SVM show that our model can effectively recommend suitable configurations and outperform the existing MtL-based methods and the well-known search-based algorithms, such as random search, Bayesian optimization, and Hyperband.

Unraveling the Complexity of Mobile Application Permissions: Strategies to Enhance Users’ Privacy Education

Smartphones and other mobile devices have seamlessly integrated into our daily lives offering a multitude of possibilities through various applications. However, this convenience comes at a cost, due to the excessive usage of device permissions claimed by the applications. The management of information privacy in mobile applications presents a formidable challenge for users. For instance, users are confronted with intricate privacy decisions, including the configuration of application permission settings. Unfortunately, many users lack adequate knowledge about how applications utilize their personal data. This research investigates the permissions of seven most popular mobile applications and provides a program to enable the extraction and categorization of permissions. The extracted information, datasets, and insights enrich the foundation of privacy education. The results can be used by educators who can develop workshops that immerse participants in this challenging topic. Therefore, this research paper contributes to the topics of privacy education and privacy awareness.